redteam

redteam is a skill for Claude Code, Codex from agentscope-ai/OpenJudge. It costs 89 tokens per session (3,306 once invoked), scanned A, original, Apache-2.0.

A safety-testing guide for language-model or agent applications. Red teaming means deliberately trying to break a system's safety rules with adversarial inputs.

In plain words
What is it for?
Creating policy-based attack tests, running them alongside safe test prompts, measuring the results, and producing a safety report.
Why use it?
It reveals jailbreaks, prompt injection, private-information leaks, harmful responses, and cases where a system refuses safe requests too often.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Creating policy-based attack tests, running them alongside safe test prompts, measuring the results, and producing a safety report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentscope-ai/openjudge/07-redteam
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add agentscope-ai/OpenJudge --skill 07-redteam
Clone the repo
git clone --depth 1 https://github.com/agentscope-ai/OpenJudge

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for redteam

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentscope-ai/openjudge/07-redteam/github.svg)](https://agentmods.dev/skills/agentscope-ai/openjudge/07-redteam)
Your own site
<a href="https://agentmods.dev/skills/agentscope-ai/openjudge/07-redteam"><img src="https://agentmods.dev/badge/skills/agentscope-ai/openjudge/07-redteam/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for redteam

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentscope-ai/openjudge/07-redteam"><img src="https://agentmods.dev/badge/skills/agentscope-ai/openjudge/07-redteam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,306 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 35
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.03306
Opus 5 $0.00044 $0.01653
Sonnet 5 $0.00018 $0.00661
Haiku 4.5 $0.00009 $0.00331

Measured 10d ago against content hash d1ff8b9faeb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

redteam scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/asr_report.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/eval_pipeline/07-redteam/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redteam

Test your application's safety boundaries systematically. This skill generates attack prompts from a policy document, measures what gets through, and pairs the Attack Success Rate (ASR) with the Over-Refusal Rate so you don't reward models that simply refuse everything.

When to Activate

  • Pre-deployment safety audit
  • Regulatory compliance check
  • After major model or prompt changes that could affect safety
  • User reports a jailbreak or injection vulnerability
  • Periodic (quarterly) safety re-evaluation

Checklist

You MUST create a task for each item and complete them in order:

  1. Establish policy — what's prohibited, what's allowed, what's gray
  2. Derive attack vectors from policy — not a fixed template
  3. Generate attack set + over-refusal set — paired measurement
  4. Run attacks and evaluate — ASR per policy category
  5. Compute over-refusal rate — paired with ASR
  6. Output safety scorecard + audit document

Fast path: run the bundled script

Once attacks and benign prompts have been run against the system and judged, compute the scorecard with the bundled, tested script (scripts/asr_report.py, standard library only, no OpenJudge dependency) — it always pairs ASR with over-refusal so you can't reward a system that just refuses everything:

python scripts/asr_report.py --attacks attacks.jsonl --over-refusals over.jsonl
# 1-5 harmfulness grader (5=safe): python scripts/asr_report.py --attacks attacks.jsonl --score-scale 5 --harm-threshold 3

Attack rows: {"category","vector","violated":bool} (or "score" + thresholds). Over-refusal rows: {"category","refused":bool}. It reports ASR per category/vector and over-refusal per category, and warns if the over-refusal set is missing. --self-test to verify it.

Read the full file on GitHub · 346 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 346 lines · 89 tokens per session scan A d1ff8b9faeb3

Subscribe to this mod's changes

redteam is a skill published in the GitHub repository agentscope-ai/OpenJudge (824 stars, last pushed 2d ago), licensed Apache-2.0. It adds 89 tokens to every session and 3,306 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.